Explain any concept: Segment anything meets concept-based explanation
EXplainable AI (XAI) is an essential topic to improve human understanding of deep neural
networks (DNNs) given their black-box internals. For computer vision tasks, mainstream …
networks (DNNs) given their black-box internals. For computer vision tasks, mainstream …
On the coherency of quantitative evaluation of visual explanations
B Vandersmissen, J Oramas - Computer Vision and Image Understanding, 2024 - Elsevier
Recent years have shown an increased development of methods for justifying the
predictions of neural networks through visual explanations. These explanations usually take …
predictions of neural networks through visual explanations. These explanations usually take …
[HTML][HTML] An interpretable decision-support model for breast cancer diagnosis using histopathology images
Microscopic examination of biopsy tissue slides is perceived as the gold-standard
methodology for the confirmation of presence of cancer cells. Manual analysis of an …
methodology for the confirmation of presence of cancer cells. Manual analysis of an …
[HTML][HTML] Where is my attention? An explainable AI exploration in water detection from SAR imagery
Attention mechanisms have found extensive application in Deep Neural Networks (DNNs),
with numerous experiments over time showcasing their efficacy in improving the overall …
with numerous experiments over time showcasing their efficacy in improving the overall …
Deep spatial context: when attention-based models meet spatial regression
P Tomaszewska, E Sienkiewicz, MP Hoang… - arxiv preprint arxiv …, 2024 - arxiv.org
We propose'Deep spatial context'(DSCon) method, which serves for investigation of the
attention-based vision models using the concept of spatial context. It was inspired by …
attention-based vision models using the concept of spatial context. It was inspired by …
T-TAME: Trainable Attention Mechanism for Explaining Convolutional Networks and Vision Transformers
The development and adoption of Vision Transformers and other deep-learning
architectures for image classification tasks has been rapid. However, the “black box” nature …
architectures for image classification tasks has been rapid. However, the “black box” nature …
P-TAME: Explain Any Image Classifier with Trained Perturbations
The adoption of Deep Neural Networks (DNNs) in critical fields where predictions need to be
accompanied by justifications is hindered by their inherent black-box nature. In this paper …
accompanied by justifications is hindered by their inherent black-box nature. In this paper …
Explainable Video Summarization for Advancing Media Content Production
This chapter focuses on explainable video summarization, a technology that could
significantly advance the content production workflow of Media organizations. It starts by …
significantly advance the content production workflow of Media organizations. It starts by …
[PDF][PDF] Sentinel-2 MSI data for active fire detection in major fire-prone biomes: A multi-criteria approach
ABSTRACT Sentinel-2 MultiSpectral Instrument (MSI) data exhibits the great potential of
enhanced spatial and temporal coverage for monitoring biomass burning which could …
enhanced spatial and temporal coverage for monitoring biomass burning which could …
A Study on the Use of Attention for Explaining Video Summarization
In this paper we present our study on the use of attention for explaining video
summarization. We build on a recent work that formulates the task, called XAI-SUM, and we …
summarization. We build on a recent work that formulates the task, called XAI-SUM, and we …